Engineering project full life cycle cost intelligent management and control system

Abstract

The invention relates to the technical field of intelligent management and control, and discloses an engineering project full life cycle cost intelligent management and control system, which comprises a data acquisition and integration module used for acquiring multi-source cost data of each stage of an engineering project and cleaning and integrating the multi-source cost data; the cost prediction and analysis module is used for performing cost prediction and real-time analysis on the integrated data; and the real-time monitoring and early warning module is used for carrying out omnibearing real-time monitoring on the engineering project cost and giving out early warning when the engineering project cost is abnormal. Through an Internet of Things data acquisition unit, an external system interface unit and a data cleaning and standardization unit in the data acquisition and integration module, comprehensive acquisition of multi-source cost data in each stage of an engineering project is realized, and denoising, de-duplication processing and format conversion are performed on the acquired multi-source heterogeneous data; the accuracy and consistency of the data are ensured, and a high-quality data basis is provided for subsequent cost prediction, analysis, monitoring and decision making.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent management and control, in particular to an intelligent management and control system for the whole life cycle cost of an engineering project. BACKGROUND

[0002] Engineering project cost management refers to a management process of realizing project cost goals and improving project economic benefits through a series of activities such as cost prediction, planning, control, accounting, analysis and assessment of each stage of a project in the whole life cycle of the project. It runs through all aspects of the project, such as planning, design, construction and acceptance, and plays a key role in the smooth progress and final profit of the project.

[0003] After searching, it is found that in the traditional engineering project cost management process, there are problems such as difficulty in data acquisition and processing, untimely monitoring and early warning, lack of scientific basis for decision-making, and great data security risks. On the one hand, the cost data generated at each stage of the engineering project is scattered in different systems and links, and the data format is various and the standard is not unified, which leads to incomplete data collection, great difficulty in cleaning and integration, and difficulty in providing accurate and effective data basis; on the other hand, the existing cost monitoring is often limited to a single dimension or is lagging, and cannot provide full-time monitoring and intelligent early warning for project cost, which is easy to cause cost out of control. In addition, the information sharing between the participants of the project is not smooth, the collaborative work efficiency is low, the managers lack sufficient data support and scientific evaluation scheme when making decisions, and it is difficult to make the optimal decision. At the same time, the cost data has the risk of being tampered with and leaked in the storage and transmission process, and the security and traceability of the data are difficult to guarantee. SUMMARY

[0004] (I) Technical problems solved

[0005] In view of the deficiencies of the prior art, the present application provides an intelligent management and control system for the whole life cycle cost of an engineering project, which solves the problem of low work efficiency in the background art.

[0006] (II) Technical solutions

[0007] To achieve the above purpose, the present application is implemented by the following technical solutions: an intelligent management and control system for the whole life cycle cost of an engineering project, comprising:

[0008] a data acquisition and integration module for acquiring multi-source cost data of each stage of the engineering project and cleaning and integrating the data;

[0009] a cost prediction and analysis module for predicting and analyzing the cost of the integrated data in real time;

[0010] a real-time monitoring and early warning module for monitoring the cost of the engineering project in all directions in real time and issuing an early warning when an anomaly occurs;

[0011] A collaborative management module to realize information sharing and collaborative work of each participant of the engineering project;

[0012] A decision support module to provide decision suggestions for project managers based on data analysis;

[0013] A blockchain data security module to ensure the non-tamperability and traceability of cost data by using distributed ledger technology;

[0014] A digital twin simulation module to build a digital twin of the engineering project for cost dynamic simulation and risk rehearsal;

[0015] A reinforcement learning decision module to generate and optimize cost control decision strategies by reinforcement learning algorithm.

[0016] Preferably, the blockchain data security module includes a consortium chain unit, a distributed ledger unit, and a smart contract execution unit. The consortium chain unit allocates node permissions to the design unit, the construction unit, the supervision unit, and the owner participant. The distributed ledger unit encrypts and stores cost-related data such as material procurement contracts, engineering progress payment records, and design change costs, and synchronously updates them. The smart contract execution unit writes key management processes such as engineering payment process and material acceptance process into smart contracts and automatically executes them.

[0017] Preferably, in the smart contract execution unit, an adaptive dynamic smart contract architecture is constructed, and is divided into a basic contract layer and a dynamic strategy layer. The basic contract layer stores core rules, including but not limited to basic conditions for engineering payment and basic standards for material acceptance, which need strict consensus of multiple parties for modification. The dynamic strategy layer allows contract administrators to initiate rule adjustment requests within the permission range according to preset conditions such as market material price fluctuation exceeding threshold value and engineering progress deviation exceeding certain proportion. During the adjustment process, asymmetric encryption and threshold signature technology are used. When the node signatures that meet the threshold conditions are collected, the dynamic strategy layer rules are automatically updated without the need to redeploy the contract, realizing quick and flexible adjustment. Specifically, when the market material price fluctuation exceeds the threshold value or the engineering progress deviation exceeds the certain proportion, the dynamic strategy layer rule adjustment is triggered, and the triggering conditions are as follows:

[0018] Price fluctuation threshold: Price_deviation>Threshold_P;

[0019] Progress deviation threshold: Schedule_deviation>Threshold_S;

[0020] Wherein, Price_deviation is the difference between the real-time price and the benchmark price, Threshold_P is the preset price fluctuation threshold, Schedule_deviation is the difference between the actual progress and the planned progress, and Threshold_S is the preset progress deviation threshold.

[0021] In addition, the signature verification formula is as follows: threshold signature technology is adopted, and the following conditions need to be met , wherein is the minimum number of required signatures, is the total number of nodes, and it is obtained that Valid_signatures≥ , wherein When the above conditions are met, the dynamic strategy layer rule is automatically updated.

[0022] Preferably, the digital twin simulation module comprises an integration unit, a real-time data mapping unit and a cost element association unit, the integration unit constructs a three-dimensional dynamic digital twin model of the engineering project through BIM and GIS, the real-time data mapping unit maps the topographic change and building structure construction progress data collected by the Internet of Things equipment on the construction site to the digital twin in real time, and the cost element association unit associates and maps the cost elements of material consumption, equipment rental fee and labor cost distribution with the physical components of the digital twin, wherein the material consumption, equipment rental fee and labor cost are associated with the physical components of the digital twin, and the logical model uses the following formula: , wherein is the total cost, is the consumption of the i-th material, is the unit price of the corresponding material, is the i-th equipment rental time, is the unit price of the corresponding equipment rental, is the i-th labor hours, is the unit price of the corresponding labor, , the number of categories of materials, equipment and labor.

[0023] Preferably, the digital twin simulation module further comprises a risk factor input interface unit, a cost influence simulation unit and a quantitative evaluation output unit, the risk factor input interface unit is used to input the risk factors of extreme weather, material price fluctuation and design change, the cost influence simulation unit simulates the influence path and degree of the risk factors on the project cost through the digital twin and the input risk factors, and the quantitative evaluation output unit outputs the quantitative evaluation results of the cost of time extension, additional equipment rental fees and labor cost caused by the risk factors.

[0024] Preferably, the reinforcement learning decision module comprises a state input unit, a reward function design unit, a policy training unit, and a dynamic decision unit, the state input unit is used to input the cost data, risk factors, and decision history of each stage of the project life cycle as the state input, the reward function design unit takes the cost control target of the engineering project as the reward function, the policy training unit is used to train the reinforcement learning model with historical project data to generate an optimal decision strategy library, and the dynamic decision unit is used to perceive the state change of the project in real time, match the optimal decision scheme from the decision strategy library, and dynamically optimize and adjust.

[0025] Preferably, in the dynamic decision unit, when the construction progress lags behind, the response scheme of adjusting the construction process and deploying idle equipment resources is called from the decision strategy library, the decision scheme execution effect is simulated through the digital twin, the influence on the cost is evaluated, and finally the decision strategy is adaptively iteratively optimized according to the actual feedback cost change result of the project.

[0026] Preferably, the data collection and integration module comprises an Internet of Things data collection unit, an external system interface unit, and a data cleaning and standardization unit, the Internet of Things data collection unit collects real-time data through the load sensor, equipment GPS positioning device, and personnel work time recording device deployed on the construction site, the external system interface unit is used to interface with the design software, contract management software, and financial software external systems to obtain design cost, contract amount, and financial expenditure data, and the data cleaning and standardization unit performs denoising, deduplication processing on the collected multi-source heterogeneous data, and format conversion according to the unified data standard.

[0027] Preferably, the real-time monitoring and early warning module comprises a multi-dimensional monitoring unit, a threshold setting unit, an intelligent early warning unit, and a prediction and early warning unit, the multi-dimensional monitoring unit performs all-around real-time monitoring on material inventory, equipment operating condition, personnel working state, and construction progress, the threshold setting unit sets the early warning threshold for the key parameters of cost deviation rate, progress deviation rate, and quality index, the intelligent early warning unit is used to automatically send early warning information containing early warning type, reason, influence, and recommended measures when the actual index deviates from the threshold, and the prediction and early warning unit predicts possible risks through historical data and real-time monitoring information and issues early warning in advance.

[0028] Preferably, the decision support module comprises a data visualization unit, a multi-scheme generation unit, a scheme evaluation unit and a decision recommendation unit, the data visualization unit displays cost data, progress data and quality data in the form of cost trend charts, progress Gantt charts and quality distribution charts, the multi-scheme generation unit provides project managers with multiple cost control decision schemes through big data analysis and reinforcement learning algorithms, the scheme evaluation unit simulates and evaluates the implementation effect of each decision scheme, including but not limited to cost change prediction, progress impact analysis and risk assessment, and the decision recommendation unit sorts and recommends the optimal scheme according to the actual situation of the project and the preferences of the managers.

[0029] (Three) beneficial effects

[0030] The application provides an engineering project full life cycle cost intelligent management and control system.

[0031] (1) The engineering project full life cycle cost intelligent management and control system realizes comprehensive collection of multi-source cost data of each stage of the project through the Internet of Things data collection unit, the external system interface unit and the data cleaning and standardization unit in the data collection and integration module, and performs denoising, deduplication processing and format conversion on the collected multi-source heterogeneous data, thereby ensuring the accuracy and consistency of the data and providing a high-quality data basis for subsequent cost prediction, analysis, monitoring and decision-making, and solving the problems of incomplete traditional data collection and non-uniform format.

[0032] (2) The engineering project full life cycle cost intelligent management and control system realizes all-round real-time monitoring of material inventory, equipment operating conditions, personnel working conditions and construction progress through the multi-dimensional monitoring unit, and in combination with the threshold setting unit, the intelligent early warning unit and the prediction and early warning unit, can not only automatically send early warning information containing the early warning type, reason, influence and suggested measures when the actual index deviates from the threshold, but also predict possible risks through historical data and real-time monitoring information and give early warning, thereby ensuring that the project cost is always within a controllable range and making up for the shortcomings of traditional monitoring lag and single dimension.

[0033] (3) The engineering project full life cycle cost intelligent management and control system provides scientific and intelligent decision support for project managers through the cooperation of the decision support module and the reinforcement learning decision module, effectively solves the problems of lack of data support and scientific evaluation in traditional decision-making, and significantly improves the scientificity and effectiveness of decision-making. BRIEF DESCRIPTION OF DRAWINGS

[0034] Figure 1 is a complete system framework schematic diagram of the application;

[0035] Figure 2Detailed framework schematic diagram of the data collection and integration module of the present application;

[0036] Figure 3 Detailed framework schematic diagram of the real-time monitoring and early warning module of the present application;

[0037] Figure 4 Detailed framework schematic diagram of the decision support module of the present application;

[0038] Figure 5 Detailed framework schematic diagram of the blockchain data security module of the present application;

[0039] Figure 6 Detailed framework schematic diagram of the digital twin simulation module of the present application;

[0040] Figure 7 Detailed framework schematic diagram of the reinforcement learning decision module of the present application;

[0041] Figure 8 Schematic diagram of the dynamic adjustment mechanism of the smart contract execution unit of the present application.

[0042] In the figure: 1, data collection and integration module; 2, cost prediction and analysis module; 3, real-time monitoring and early warning module; 4, collaborative management module; 5, decision support module; 6, blockchain data security module; 7, digital twin simulation module; 8, reinforcement learning decision module; 601, alliance chain unit; 602, distributed ledger unit; 603, smart contract execution unit; 701, integrated unit; 702, real-time data mapping unit; 703, cost factor correlation unit; 704, risk factor input interface unit; 705, cost influence simulation unit; 706, quantitative evaluation output unit; 801, state input unit; 802, reward function design unit; 803, strategy training unit; 804, dynamic decision unit; 101, Internet of Things data collection unit; 102, external system interface unit; 103, data cleaning and standardization unit; 301, multi-dimensional monitoring unit; 302, threshold setting unit; 303, intelligent early warning unit; 304, prediction and early warning unit; 501, data visualization unit; 502, multi-scheme generation unit; 503, scheme evaluation unit; 504, decision recommendation unit. DETAILED DESCRIPTION

[0043] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of protection of the present application.

[0044] Please refer to Figures 1-8The application provides an engineering project full life cycle cost intelligent management and control system, which comprises a data acquisition and integration module 1, a cost prediction and analysis module 2, a real-time monitoring and early warning module 3, a collaborative management module 4, a decision support module 5, a blockchain data security module 6, a digital twin simulation module 7 and a reinforcement learning decision module 8. The data acquisition and integration module 1 is used for acquiring multi-source cost data of each stage of the engineering project and performing cleaning and integration. Specifically, the data acquisition and integration module 1 comprises an Internet of Things data acquisition unit 101, an external system interface unit 102 and a data cleaning and standardization unit 103. The Internet of Things data acquisition unit 101 acquires real-time data through load sensors, equipment GPS positioning devices and personnel work time recording devices deployed on the construction site. The external system interface unit 102 is used for interfacing with design software, contract management software and financial software external systems to acquire design cost, contract amount and financial expenditure data. The data cleaning and standardization unit 103 performs denoising and deduplication processing on the acquired multi-source heterogeneous data, and performs format conversion according to a unified data standard, thereby ensuring the accuracy and consistency of the data and providing a high-quality data basis for subsequent modules.

[0045] The cost prediction and analysis module 2 is used for cost prediction and real-time analysis of the integrated data. The real-time monitoring and early warning module 3 performs all-round real-time monitoring on the engineering project cost and issues a warning when an anomaly occurs. Specifically, the real-time monitoring and early warning module 3 comprises a multi-dimensional monitoring unit 301, a threshold setting unit 302, an intelligent early warning unit 303 and a prediction and early warning unit 304. The multi-dimensional monitoring unit 301 performs all-round real-time monitoring on material inventory, equipment operating conditions, personnel working conditions and construction progress. The threshold setting unit 302 sets early warning thresholds for key parameters of cost deviation rate, progress deviation rate and quality indicators. The intelligent early warning unit 303 is used for automatically sending early warning information containing early warning type, reason, influence and suggested measures when the actual indicators deviate from the thresholds. The specific operation is as follows. First, the cost deviation rate is calculated as follows:

[0046]

[0047] Wherein, is the actual cost, is the planned cost;

[0048] Then, the progress deviation rate is calculated as follows:

[0049]

[0050] Wherein, is the actual construction period, is the planned construction period, and the early warning is triggered when the deviation rate exceeds the preset threshold.

[0051] The prediction and early warning unit 304 predicts possible risks and issues early warnings in advance through historical data and real-time monitoring information. The real-time monitoring and early warning module 3 ensures that the project cost is within a controllable range through multi-dimensional monitoring and intelligent early warning.

[0052] The collaborative management module 4 realizes information sharing and collaborative work of all participants in the engineering project. The decision support module 5 provides decision suggestions for project managers based on data analysis. Through data visualization and multi-scheme evaluation, it helps managers make more intelligent decisions. Specifically, the decision support module 5 includes a data visualization unit 501, a multi-scheme generation unit 502, a scheme evaluation unit 503, and a decision recommendation unit 504. The data visualization unit 501 displays cost data, progress data, and quality data in the form of cost trend charts, progress Gantt charts, and quality distribution charts. The multi-scheme generation unit 502 provides project managers with multiple cost control decision schemes through big data analysis and reinforcement learning algorithms. The scheme evaluation unit 503 simulates and evaluates the implementation effects of each decision scheme, including but not limited to cost change prediction, progress impact analysis, and risk assessment. The decision recommendation unit 504 sorts and recommends the optimal scheme according to the actual situation of the project and the preferences of the managers.

[0053] The blockchain data security module 6 uses distributed ledger technology to ensure the non-tamperability and traceability of cost data. Through blockchain technology, the security and transparency of data are ensured. Specifically, the blockchain data security module 6 includes a consortium chain unit 601, a distributed ledger unit 602, and an intelligent contract execution unit 603. The consortium chain unit 601 allocates node permissions for design units, construction units, supervision units, and owner participants. The distributed ledger unit 602 encrypts and stores cost-related data such as material procurement contracts, engineering progress payment records, and design change costs, and synchronously updates them. The intelligent contract execution unit 603 writes key management processes such as engineering payment processes and material acceptance processes into intelligent contracts and automatically executes them. Further, in the intelligent contract execution unit 603, an adaptive dynamic intelligent contract architecture is constructed, and it is divided into a basic contract layer and a dynamic strategy layer. The basic contract layer stores core rules, including but not limited to basic conditions for engineering payment and basic standards for material acceptance. Modification requires strict consensus among multiple parties. The dynamic strategy layer allows contract administrators to initiate rule adjustment requests within their authority range based on pre-set conditions such as market material price fluctuations exceeding a threshold or engineering progress deviation exceeding a certain percentage. During the adjustment process, asymmetric encryption and threshold signature technology are used. When the node signatures that meet the threshold conditions are collected, the dynamic strategy layer rules are automatically updated without the need to redeploy the contract, enabling rapid and flexible adjustment. Specifically, when the market material price fluctuation exceeds the threshold or the engineering progress deviation exceeds a certain percentage, the dynamic strategy layer rule adjustment is triggered. The trigger conditions are as follows:

[0054] Price_deviation>Threshold_P;

[0055] Schedule_deviation>Threshold_S;

[0056] wherein Price_deviation is the difference between real-time price and benchmark price, Threshold_P is the preset price fluctuation threshold, Schedule_deviation is the difference between actual progress and planned progress, and Threshold_S is the preset progress deviation threshold;

[0057] In addition, the signature verification formula is as follows: threshold signature technology is adopted, and the following condition needs to be met wherein is the minimum number of required signatures, is the total number of nodes, and it is obtained that Valid_signatures≥ wherein When the above conditions are met, the dynamic strategy layer rule is automatically updated.

[0058] The digital twin simulation module 7 constructs a digital twin of the engineering project to perform cost dynamic simulation and risk rehearsal. Through digital twin technology, the manager can rehearse risks in advance and develop countermeasures. Specifically, the digital twin simulation module 7 includes an integration unit 701, a real-time data mapping unit 702, and a cost element association unit 703. The integration unit 701 constructs a three-dimensional dynamic digital twin model of the engineering project through BIM and GIS. The real-time data mapping unit 702 maps the topographic changes and construction progress data collected by the Internet of Things devices on the construction site to the digital twin in real time. The cost element association unit 703 associates and maps the cost elements of material consumption, equipment rental fees, and labor cost distribution with the physical components of the digital twin. The material consumption, equipment rental fees, and labor costs are associated with the physical components of the digital twin. The logical model uses the following formula: wherein is the total cost, is the consumption of the th material, is the unit price of the corresponding material, is the rental time of the th equipment, is the unit price of the corresponding equipment rental, is the working hours of the th labor, is the unit price of the corresponding labor, , The material, equipment, artificial category number, in addition to the digital twin simulation module 7 also includes a risk factor input interface unit 704, a cost influence simulation unit 705, and a quantitative evaluation output unit 706. The risk factor input interface unit 704 is used to input the risk factors of extreme weather, material price fluctuations, and design changes. The cost influence simulation unit 705 simulates the influence path and degree of the input risk factors on the project cost through the digital twin. The quantitative evaluation output unit 706 outputs the quantitative evaluation results of the cost of time extension, additional equipment rental costs, and labor idle cost caused by risk factors. The specific simulation of the influence of extreme weather, design changes, etc. on the cost uses the following formula: Wherein, is the total risk cost increment, is the cost caused by time extension, is the additional equipment rental cost, is the labor idle cost.

[0059] The reinforcement learning decision module 8 is used to generate and optimize the cost control decision strategy through the reinforcement learning algorithm. Through the reinforcement learning algorithm, the decision strategy is continuously optimized to improve the cost control effect. Specifically, the reinforcement learning decision module 8 includes a state input unit 801, a reward function design unit 802, a policy training unit 803, and a dynamic decision unit 804. The state input unit 801 is used to input the cost data, risk factors, and decision history of each stage of the project life cycle as the state. The reward function design unit 802 takes the engineering project cost control target of cost minimization and profit maximization as the reward function. The policy training unit 803 is used to train the reinforcement learning model with historical project data to generate an optimal decision strategy library. The specific target is oriented towards cost minimization and profit maximization. The following formula is used: Wherein, is the state The reward value of the action executed, is the cost of executing the action , is the profit of executing the action , is the profit weight coefficient, and when ≥ 0, it is adjusted according to the project target.

[0060] The dynamic decision unit 804 is used to perceive the project state changes in real time, match the optimal decision scheme from the decision strategy library, and dynamically optimize and adjust. Further, when the construction progress lag is detected, the response scheme of adjusting the construction process and deploying idle equipment resources is retrieved from the decision strategy library. The execution effect of the decision scheme is simulated through the digital twin to evaluate the influence on the cost. Finally, according to the actual feedback of the cost change results, the decision strategy is adaptively iteratively optimized.

[0061] While embodiments of the application have been shown and described, it is to be understood that the application is not limited to the details of the embodiments described, since numerous changes, modifications, substitutions and variations can be made thereto without departing from the spirit and scope of the application as defined by the appended claims and their equivalents.

Claims

1. An intelligent cost management and control system for the entire life cycle of an engineering project, characterized by: include: Data collection and integration module (1), used to collect multi-source cost data from various stages of the project and to clean and integrate them; A cost prediction and analysis module (2), configured to perform cost prediction and real-time analysis on the integrated data; Real-time monitoring and early warning module (3) monitors the project cost in all aspects in real time and issues early warnings when anomalies occur; Collaborative management module (4) enables information sharing and collaborative work among all project participants; Decision support module (5), which provides decision suggestions to project managers based on data analysis; Blockchain data security module (6), which uses distributed ledger technology to ensure the immutability and traceability of cost data; Digital twin simulation module (7), building a digital twin of the engineering project to conduct dynamic cost simulation and risk rehearsal; Reinforcement learning decision module (8) is used to generate and optimize cost control decision strategies using reinforcement learning algorithms.

2. The intelligent cost management and control system for the entire life cycle of an engineering project according to claim 1 is characterized by: The blockchain data security module (6) includes an alliance chain unit (601), a distributed ledger unit (602) and a smart contract execution unit (603). The alliance chain unit (601) allocates node permissions to the design unit, the construction unit, the supervision unit and the owner. The distributed ledger unit (602) encrypts and stores and synchronously updates the cost-related data of material procurement contracts, project progress payment records and design change fees. The smart contract execution unit (603) compiles the key management processes of the project payment process and the material acceptance process into smart contracts and automatically executes them.

3. The intelligent cost management and control system for the entire life cycle of an engineering project according to claim 2 is characterized by: In the smart contract execution unit (603), an adaptive dynamic smart contract architecture is constructed and divided into a basic contract layer and a dynamic strategy layer. The basic contract layer stores core rules, including but not limited to basic conditions for project payment and basic standards for material acceptance. Modification requires strict consensus from multiple parties. The dynamic strategy layer allows the contract administrator to initiate a rule adjustment request within the scope of authority based on the preset conditions of market material price fluctuation exceeding a threshold and project progress deviation exceeding a certain ratio. During the adjustment process, asymmetric encryption and threshold signature technology are used. When the node signature that meets the threshold condition is collected, the dynamic strategy layer rules are automatically updated without redeploying the contract, achieving fast and flexible adjustment. Specifically, when the market material price fluctuation exceeds the threshold or the project progress deviation exceeds a certain ratio, the dynamic strategy layer rule adjustment is triggered. The triggering conditions are as follows: Price fluctuation threshold: Price_deviation>Threshold_P; Schedule deviation threshold: Schedule_deviation>Threshold_S; Where Price_deviation is the difference between the real-time price and the benchmark price, Threshold_P is the preset price fluctuation threshold, Schedule_deviation is the difference between the actual schedule and the planned schedule, and Threshold_S is the preset schedule deviation threshold. In addition, the signature verification formula is as follows: Using threshold signature technology, it is necessary to meet ,in is the minimum number of signatures required, is the total number of nodes, and we get: Valid_signatures≥ ,in ,When the above conditions are met, the dynamic policy layer rules are automatically updated.

4. The intelligent cost management and control system for the entire life cycle of an engineering project according to claim 1 is characterized by: The digital twin simulation module (7) includes an integration unit (701), a real-time data mapping unit (702) and a cost element association unit (703). The integration unit (701) constructs a three-dimensional dynamic digital twin model of the engineering project through BIM and GIS. The real-time data mapping unit (702) maps the terrain changes and building structure construction progress data collected by the Internet of Things equipment at the construction site to the digital twin in real time. The cost element association unit (703) associates and maps the cost elements of material consumption, equipment rental fees, and labor cost distribution with the physical components of the digital twin, wherein material consumption, equipment rental fees, labor costs, etc. are associated with the physical components of the digital twin. The logical model uses the following formula: ,in is the total cost, For the Material consumption, is the corresponding material unit price, For the Equipment rental time, is the corresponding equipment rental unit price, For the Manual working hours, For the corresponding labor unit price, 、 The number of categories of materials, equipment, and labor.

5. The intelligent cost management and control system for the entire life cycle of an engineering project according to claim 1 is characterized by: The digital twin simulation module (7) further includes a risk factor input interface unit (704), a cost impact simulation unit (705) and a quantitative evaluation output unit (706), wherein the risk factor input interface unit (704) is used to input risk factors such as extreme weather, material price fluctuations, and design changes; the cost impact simulation unit (705) simulates the path and extent of the impact of the risk factors on the project cost through the digital twin and the input risk factors; and the quantitative evaluation output unit (706) outputs quantitative evaluation results of the project duration extension cost, equipment rental additional cost, and labor idleness cost caused by the risk factors.

6. The intelligent cost management and control system for the entire life cycle of an engineering project according to claim 1 is characterized by: The reinforcement learning decision module (8) includes a state input unit (801), a reward function design unit (802), a strategy training unit (803) and a dynamic decision unit (804), wherein the state input unit (801) is used to take the cost data, risk factors and decision history of each stage of the project life cycle as state input, the reward function design unit (802) takes the engineering project cost control goal of minimizing cost and maximizing profit as the reward function, the strategy training unit (803) is used to train the reinforcement learning model with historical project data and generate an optimal decision strategy library, and the dynamic decision unit (804) is used to perceive the change of project state in real time, match the optimal decision plan from the decision strategy library and dynamically optimize and adjust.

7. The intelligent cost management and control system for the entire life cycle of an engineering project according to claim 6 is characterized by: In the dynamic decision-making unit (804), when it is detected that the construction progress is lagging behind, the response plan of adjusting the construction process and allocating idle equipment resources is retrieved from the decision-making strategy library, and the execution effect of the decision-making plan is simulated through the digital twin to evaluate the impact on the cost. Finally, according to the cost change results actually fed back by the project, the decision-making strategy is adaptively iteratively optimized.

8. The intelligent cost management and control system for the entire life cycle of an engineering project according to claim 1 is characterized by: The data acquisition and integration module (1) includes an Internet of Things data acquisition unit (101), an external system interface unit (102) and a data cleaning and standardization unit (103). The Internet of Things data acquisition unit (101) collects real-time data through a scale sensor, a GPS positioning device for equipment, and a time recording device for personnel deployed at the construction site. The external system interface unit (102) is used to connect with the external systems of design software, contract management software, and financial software to obtain design cost, contract amount, and financial expenditure data. The data cleaning and standardization unit (103) performs denoising and deduplication processing on the collected multi-source heterogeneous data, and performs format conversion according to a unified data standard.

9. The intelligent cost management and control system for the entire life cycle of an engineering project according to claim 1 is characterized by: The real-time monitoring and early warning module (3) includes a multi-dimensional monitoring unit (301), a threshold setting unit (302), an intelligent early warning unit (303) and a prediction and early warning unit (304). The multi-dimensional monitoring unit (301) performs all-round real-time monitoring of material inventory, equipment operation status, personnel work status and construction progress. The threshold setting unit (302) sets early warning thresholds for key parameters such as cost deviation rate, progress deviation rate and quality indicators. The intelligent early warning unit (303) is used to automatically send early warning information including early warning type, cause, impact and recommended measures when the actual indicator deviates from the threshold. The prediction and early warning unit (304) predicts possible risks and issues early warnings based on historical data and real-time monitoring information.

10. The intelligent cost management and control system for the entire life cycle of an engineering project according to claim 1 is characterized by: The decision support module (5) includes a data visualization unit (501), a multi-scheme generation unit (502), a scheme evaluation unit (503) and a decision recommendation unit (504). The data visualization unit (501) displays cost data, schedule data and quality data in the form of cost trend charts, schedule Gantt charts and quality distribution charts. The multi-scheme generation unit (502) provides project managers with a variety of cost control decision schemes through big data analysis and reinforcement learning algorithms. The scheme evaluation unit (503) simulates and evaluates the implementation effects of each decision scheme, including but not limited to cost change prediction, schedule impact analysis and risk assessment. The decision recommendation unit (504) ranks the decision schemes and recommends the best scheme based on the actual situation of the project and the manager's preferences.

Images